Political Affiliation Predictions — (166 people classified)

Model

Logistic Regression

Test Accuracy

0.590

Number of Classes Predicted

3

Class Distribution
affiliation count percent
0 Independent 62 37.3
1 Democrat 60 36.1
2 Republican 44 26.5 
Pipeline(steps=[('preprocess',
                 ColumnTransformer(transformers=[('num', StandardScaler(),
                                                  ['Q2', 'Q15', 'Q16', 'Q17']),
                                                 ('cat',
                                                  OneHotEncoder(handle_unknown='ignore'),
                                                  ['Q1', 'Q4', 'Q5', 'Q6', 'Q7',
                                                   'Q8', 'Q9', 'Q10', 'Q11',
                                                   'Q12', 'Q13', 'Q14',
                                                   'Q18'])])),
                ('model',
                 LogisticRegression(max_iter=5000, multi_class='multinomial'))])
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
Predicted Democrat Independent Republican Row Total
Actual
Democrat 45 11 3 59
Independent 13 36 7 56
Republican 4 7 43 54
Column Total 62 54 53 169
Summary
Metric Value
Accuracy 0.59036
Total Predictions 166
Number of Classes 3